© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2873
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sometimes" and expressions of uncertainty or feelings about the passage of time and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "sometimes" or similar adverbs

    np_acts-logits-general · gemini-2.0-flash

    sometimes or even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     always
    -0.96
     sempre
    -0.95
     siempre
    -0.86
    always
    -0.85
     constantly
    -0.84
     continually
    -0.82
     altid
    -0.78
    sempre
    -0.76
     vždy
    -0.76
     всегда
    -0.74
    POSITIVE LOGITS
     бывает
    0.89
     disambiguazione
    0.87
     chiar
    0.80
    甚至是
    0.79
     sogar
    0.77
     downright
    0.74
     even
    0.72
     бывают
    0.72
     addirittura
    0.72
     zelfs
    0.70
    Activations Density 0.308%

    No Known Activations